Crime events and time

Crime events v.s. Time

Number of cirime events each month

sub_crime_month = 
  raw_sub_crime %>% 
  filter(start_date > "2021-01-01") %>% 
  select(start_date, start_time, crime_event, law_cat) %>% 
  mutate(start_date = substring(start_date, 1, 7))
  
plot_1 = 
  sub_crime_month %>% 
  group_by(start_date) %>% 
  summarise(event_num = n()) %>% 
  plot_ly(
    x = ~start_date, y = ~event_num, type = "bar"
  )

layout(plot_1, title = "Crime events over month", xaxis = list(title = "Month"), yaxis = list(title = "Number of Crime Events"))

Number of crime events each week

sub_crime_week = 
  raw_sub_crime %>% 
  select(start_date, start_time, crime_event, law_cat) %>% 
  mutate(week = cut.Date(start_date, breaks = "1 week", labels = FALSE)) %>% 
  arrange(week) %>% 
  group_by(week) %>% 
  summarise(event_num = n())
  
plot_2 = 
  sub_crime_week %>% 
    plot_ly(
    x = ~week, y = ~event_num, type = "scatter", mode = "marker"
  )

layout(plot_2, title = "Crime events over weeks", xaxis = list(title = "Week"), yaxis = list(title = "Number of Crime Events"))

Top 5 crime events v.s. Occurrence time

crime_occ_time = 
  raw_sub_crime %>% 
  mutate(event_time = ordered(event_time, levels = c("2 AM","6 AM","10 AM","2 PM","6 PM","10 PM"))) %>% 
  filter(crime_event %in% c("criminal mischief & related of","assault 3 & related offenses","harrassment 2","grand larceny","dangerous drugs"))

plot_3 = 
  crime_occ_time %>% 
  ggplot(aes(x = event_time, fill = crime_event)) + 
  geom_histogram(stat = "count", width = 0.9, height = 2) + 
  labs(
    title = "Frequency of crime events v.s. Time points", 
    x = "Occurrence time", 
    y = "Frequency of crime events") + 
  theme_bw() + 
  theme(
    plot.title = element_text(hjust = 1), 
    legend.position = "bottom",
    legend.text = element_text(size = 8)) + 
  guides(col = guide_legend(nrow = 2))

ggplotly(plot_3) %>%
  layout(legend = list(
      orientation = "h",
      xanchor = "center",
      yanchor = "top",
      x = 0.3,
      y = - 0.3
    )
  )

Degrees of crime event

sub_crime_degree = 
  raw_sub_crime %>% 
  filter(crime_event %in% c("criminal mischief & related of","assault 3 & related offenses","harrassment 2","grand larceny","dangerous drugs","felony assault", "robbery", "petit larceny", "forgery", "sex crimes")) %>% 
  count(crime_event, law_cat)

plot_4 = 
  sub_crime_degree %>% 
    plot_ly(
    x = ~crime_event, y = ~n, color = ~law_cat, type = "bar"
  )

layout(plot_4, title = "Crime Events Numbers each degree", xaxis = list(title = "Crime events"), yaxis = list(title = "Number of Crime Events"))

Proceeding time

crime_prcd_time = 
  raw_sub_crime %>% 
  drop_na(start_time, end_time) %>%
  mutate(prcd_time = difftime(end, start, units = "mins")) %>% 
  filter(prcd_time < 35) %>% 
  filter(prcd_time != 0) %>% 
  mutate(quarters = quarters(as.Date(start_date)))

plot_5 = 
  crime_prcd_time %>% 
  plot_ly(y = ~ prcd_time, color = ~ law_cat, type = "box")

layout(plot_5, title = "Crime type", xaxis = list(title = "Proceeding time"), yaxis = list(title = "Crime type v.s. Proceeding time (mins)")
    )

Day of week v.s. Occurrence time

sub_crime_dow = 
  raw_sub_crime %>% 
  mutate(day_of_week = wday(as.Date(start_date), label=TRUE, abbr = FALSE)) %>% 
  mutate(day_of_week = fct_relevel(day_of_week, "Saturday", "Friday", "Thursday", "Wednesday", "Tuesday", "Monday", "Sunday")) %>% 
  separate(start_time, into = c("hour", "minute", "second"), sep = ":") %>% 
  select(day_of_week, hour, crime_event) %>% 
  group_by(day_of_week, hour) %>% 
  summarise(crime_num = n())

plot_6 = 
  sub_crime_dow %>% 
  plot_ly(
    x = ~ hour, y = ~ day_of_week, z = ~ crime_num, type = "heatmap", colors = "BuPu"
  ) %>%
  colorbar(title = "Events Number", x = 1.1, y = 0.8) 

layout(plot_6, title = "Crime frequency: Day v.s. Hour", xaxis = list(title = "Hour"), yaxis = list(title = "Day of week")
    )